Mirrors/dots.ocr
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

udpate wechat, fix some little bugs

Browse Source
This commit is contained in:
zhangwei13
2025-08-05 11:34:53 +08:00
parent b370ec0f0c
commit ae0ca3a8be
4 changed files with 2 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+1 -1
View File
@@ -1139,7 +1139,7 @@ print(output_text)
# Parse a single image # Parse a single image
python3 dots_ocr/parser.py demo/demo_image1.jpg python3 dots_ocr/parser.py demo/demo_image1.jpg
# Parse a single PDF # Parse a single PDF
python3 dots_ocr/parser.py demo/demo_pdf1.pdf --num_threads 64 # try bigger num_threads for pdf with a large number of pages python3 dots_ocr/parser.py demo/demo_pdf1.pdf --num_thread 64 # try bigger num_threads for pdf with a large number of pages
# Layout detection only # Layout detection only
python3 dots_ocr/parser.py demo/demo_image1.jpg --prompt prompt_layout_only_en python3 dots_ocr/parser.py demo/demo_image1.jpg --prompt prompt_layout_only_en
assets/wechat.jpg
BIN
View File
Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 203 KiB

After

Width:  |  Height:  |  Size: 261 KiB

dots_ocr/parser.py
+1 -1
View File
@@ -190,7 +190,7 @@ class DotsOCRParser:
def parse_pdf(self, input_path, filename, prompt_mode, save_dir): def parse_pdf(self, input_path, filename, prompt_mode, save_dir):
print(f"loading pdf: {input_path}") print(f"loading pdf: {input_path}")
images_origin = load_images_from_pdf(input_path) images_origin = load_images_from_pdf(input_path, dpi=self.dpi)
total_pages = len(images_origin) total_pages = len(images_origin)
tasks = [ tasks = [
{ {
requirements.txt
-1
View File
@@ -1,4 +1,3 @@
# 生产环境依赖
# streamlit # streamlit
gradio gradio
gradio_image_annotation gradio_image_annotation